Mickey's repositories
baselines
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
bolt
Bolt is a deep learning library with high performance and heterogeneous flexibility.
chinese_text_normalization
Chinese text normalization for speech processing
distiller
Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller
easy-rl
强化学习中文教程（蘑菇书），在线阅读地址：https://datawhalechina.github.io/easy-rl/
EasyOCR
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
espnet
End-to-End Speech Processing Toolkit
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
GPTQ-for-LLaMa
4 bits quantization of LLaMA using GPTQ
k2
FSA/FST algorithms, differentiable, with PyTorch compatibility.
kaldi
kaldi-asr/kaldi is the official location of the Kaldi project.
llama
Inference code for LLaMA models
neural_sp
End-to-end ASR/LM implementation with PyTorch
nppPluginList
The official collection of Notepad++ plugins.
Pretrained-Language-Model
Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.
PyTorch-ONNX-TFLite
Conversion of PyTorch Models into TFLite
RL4LMs
A modular RL library to fine-tune language models to human preferences
scaper
A library for soundscape synthesis and augmentation
silero-vad
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
ThinkDSP
Think DSP: Digital Signal Processing in Python, by Allen B. Downey.
TinyNeuralNetwork
TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
video-subtitle-extractor
视频硬字幕提取，生成srt文件。无需申请第三方API，本地实现文本识别。基于深度学习的视频字幕提取框架，包含字幕区域检测、字幕内容提取。A GUI tool for extracting hard-coded subtitle (hardsub) from videos and generating srt files.
WanJuan1.0
万卷1.0多模态语料
wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
whisper
Robust Speech Recognition via Large-Scale Weak Supervision